English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents a novel method for attitude estimation of an object in 3Dspace by incremental learning of the Long-Short Term Memory (LSTM) network.Gyroscope, accelerometer, and magnetometer are few widely used sensors inattitude estimation applications. Traditionally, multi-sensor fusion methodssuch as the Extended Kalman Filter and Complementary Filter are employed tofuse the measurements from these sensors. However, these methods exhibitlimitations in accounting for the uncertainty, unpredictability, and dynamicnature of the motion in real-world situations. In this paper, the inertialsensors data are fed to the LSTM network which are then updated incrementallyto incorporate the dynamic changes in motion occurring in the run time. Therobustness and efficiency of the proposed framework is demonstrated on thedataset collected from a commercially available inertial measurement unit. Theproposed framework offers a significant improvement in the results compared tothe traditional method, even in the case of a highly dynamic environment. TheLSTM framework-based attitude estimation approach can be deployed on a standardAI-supported processing module for real-time applications.

Incremental learning of LSTM framework for sensor fusion in attitude estimation